From 97b713ba3ebaa6c8d84c2c720f5468a7c6a6eb4e Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 14 Jan 2015 10:42:31 +0100 Subject: fs: kill BDI_CAP_SWAP_BACKED This bdi flag isn't too useful - we can determine that a vma is backed by either swap or shmem trivially in the caller. This also allows removing the backing_dev_info instaces for swap and shmem in favor of noop_backing_dev_info. Signed-off-by: Christoph Hellwig Reviewed-by: Tejun Heo Reviewed-by: Jan Kara Signed-off-by: Jens Axboe --- include/linux/backing-dev.h | 13 ------------- 1 file changed, 13 deletions(-) (limited to 'include/linux/backing-dev.h') diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 5da6012b7a14..e936cea856dc 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -238,8 +238,6 @@ int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio); * BDI_CAP_WRITE_MAP: Can be mapped for writing * BDI_CAP_EXEC_MAP: Can be mapped for execution * - * BDI_CAP_SWAP_BACKED: Count shmem/tmpfs objects as swap-backed. - * * BDI_CAP_STRICTLIMIT: Keep number of dirty pages below bdi threshold. */ #define BDI_CAP_NO_ACCT_DIRTY 0x00000001 @@ -250,7 +248,6 @@ int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio); #define BDI_CAP_WRITE_MAP 0x00000020 #define BDI_CAP_EXEC_MAP 0x00000040 #define BDI_CAP_NO_ACCT_WB 0x00000080 -#define BDI_CAP_SWAP_BACKED 0x00000100 #define BDI_CAP_STABLE_WRITES 0x00000200 #define BDI_CAP_STRICTLIMIT 0x00000400 @@ -329,11 +326,6 @@ static inline bool bdi_cap_account_writeback(struct backing_dev_info *bdi) BDI_CAP_NO_WRITEBACK)); } -static inline bool bdi_cap_swap_backed(struct backing_dev_info *bdi) -{ - return bdi->capabilities & BDI_CAP_SWAP_BACKED; -} - static inline bool mapping_cap_writeback_dirty(struct address_space *mapping) { return bdi_cap_writeback_dirty(mapping->backing_dev_info); @@ -344,11 +336,6 @@ static inline bool mapping_cap_account_dirty(struct address_space *mapping) return bdi_cap_account_dirty(mapping->backing_dev_info); } -static inline bool mapping_cap_swap_backed(struct address_space *mapping) -{ - return bdi_cap_swap_backed(mapping->backing_dev_info); -} - static inline int bdi_sched_wait(void *word) { schedule(); -- cgit v1.2.3 From b4caecd48005fbed3949dde6c1cb233142fd69e9 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 14 Jan 2015 10:42:32 +0100 Subject: fs: introduce f_op->mmap_capabilities for nommu mmap support Since "BDI: Provide backing device capability information [try #3]" the backing_dev_info structure also provides flags for the kind of mmap operation available in a nommu environment, which is entirely unrelated to it's original purpose. Introduce a new nommu-only file operation to provide this information to the nommu mmap code instead. Splitting this from the backing_dev_info structure allows to remove lots of backing_dev_info instance that aren't otherwise needed, and entirely gets rid of the concept of providing a backing_dev_info for a character device. It also removes the need for the mtd_inodefs filesystem. Signed-off-by: Christoph Hellwig Reviewed-by: Tejun Heo Acked-by: Brian Norris Signed-off-by: Jens Axboe --- include/linux/backing-dev.h | 33 ++++----------------------------- 1 file changed, 4 insertions(+), 29 deletions(-) (limited to 'include/linux/backing-dev.h') diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index e936cea856dc..478f95d92d73 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -114,7 +114,7 @@ int bdi_register(struct backing_dev_info *bdi, struct device *parent, const char *fmt, ...); int bdi_register_dev(struct backing_dev_info *bdi, dev_t dev); void bdi_unregister(struct backing_dev_info *bdi); -int __must_check bdi_setup_and_register(struct backing_dev_info *, char *, unsigned int); +int __must_check bdi_setup_and_register(struct backing_dev_info *, char *); void bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages, enum wb_reason reason); void bdi_start_background_writeback(struct backing_dev_info *bdi); @@ -228,42 +228,17 @@ int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio); * BDI_CAP_NO_ACCT_DIRTY: Dirty pages shouldn't contribute to accounting * BDI_CAP_NO_WRITEBACK: Don't write pages back * BDI_CAP_NO_ACCT_WB: Don't automatically account writeback pages - * - * These flags let !MMU mmap() govern direct device mapping vs immediate - * copying more easily for MAP_PRIVATE, especially for ROM filesystems. - * - * BDI_CAP_MAP_COPY: Copy can be mapped (MAP_PRIVATE) - * BDI_CAP_MAP_DIRECT: Can be mapped directly (MAP_SHARED) - * BDI_CAP_READ_MAP: Can be mapped for reading - * BDI_CAP_WRITE_MAP: Can be mapped for writing - * BDI_CAP_EXEC_MAP: Can be mapped for execution - * * BDI_CAP_STRICTLIMIT: Keep number of dirty pages below bdi threshold. */ #define BDI_CAP_NO_ACCT_DIRTY 0x00000001 #define BDI_CAP_NO_WRITEBACK 0x00000002 -#define BDI_CAP_MAP_COPY 0x00000004 -#define BDI_CAP_MAP_DIRECT 0x00000008 -#define BDI_CAP_READ_MAP 0x00000010 -#define BDI_CAP_WRITE_MAP 0x00000020 -#define BDI_CAP_EXEC_MAP 0x00000040 -#define BDI_CAP_NO_ACCT_WB 0x00000080 -#define BDI_CAP_STABLE_WRITES 0x00000200 -#define BDI_CAP_STRICTLIMIT 0x00000400 - -#define BDI_CAP_VMFLAGS \ - (BDI_CAP_READ_MAP | BDI_CAP_WRITE_MAP | BDI_CAP_EXEC_MAP) +#define BDI_CAP_NO_ACCT_WB 0x00000004 +#define BDI_CAP_STABLE_WRITES 0x00000008 +#define BDI_CAP_STRICTLIMIT 0x00000010 #define BDI_CAP_NO_ACCT_AND_WRITEBACK \ (BDI_CAP_NO_WRITEBACK | BDI_CAP_NO_ACCT_DIRTY | BDI_CAP_NO_ACCT_WB) -#if defined(VM_MAYREAD) && \ - (BDI_CAP_READ_MAP != VM_MAYREAD || \ - BDI_CAP_WRITE_MAP != VM_MAYWRITE || \ - BDI_CAP_EXEC_MAP != VM_MAYEXEC) -#error please change backing_dev_info::capabilities flags -#endif - extern struct backing_dev_info default_backing_dev_info; extern struct backing_dev_info noop_backing_dev_info; -- cgit v1.2.3 From de1414a654e66b81b5348dbc5259ecf2fb61655e Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 14 Jan 2015 10:42:36 +0100 Subject: fs: export inode_to_bdi and use it in favor of mapping->backing_dev_info Now that we got rid of the bdi abuse on character devices we can always use sb->s_bdi to get at the backing_dev_info for a file, except for the block device special case. Export inode_to_bdi and replace uses of mapping->backing_dev_info with it to prepare for the removal of mapping->backing_dev_info. Signed-off-by: Christoph Hellwig Reviewed-by: Tejun Heo Reviewed-by: Jan Kara Signed-off-by: Jens Axboe --- include/linux/backing-dev.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux/backing-dev.h') diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 478f95d92d73..ed59dee03a71 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -106,6 +106,8 @@ struct backing_dev_info { #endif }; +struct backing_dev_info *inode_to_bdi(struct inode *inode); + int __must_check bdi_init(struct backing_dev_info *bdi); void bdi_destroy(struct backing_dev_info *bdi); @@ -303,12 +305,12 @@ static inline bool bdi_cap_account_writeback(struct backing_dev_info *bdi) static inline bool mapping_cap_writeback_dirty(struct address_space *mapping) { - return bdi_cap_writeback_dirty(mapping->backing_dev_info); + return bdi_cap_writeback_dirty(inode_to_bdi(mapping->host)); } static inline bool mapping_cap_account_dirty(struct address_space *mapping) { - return bdi_cap_account_dirty(mapping->backing_dev_info); + return bdi_cap_account_dirty(inode_to_bdi(mapping->host)); } static inline int bdi_sched_wait(void *word) -- cgit v1.2.3 From df0ce26cb4ee8bc233d50213b97213532aff0a3c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 14 Jan 2015 10:42:41 +0100 Subject: fs: remove default_backing_dev_info Now that default_backing_dev_info is not used for writeback purposes we can git rid of it easily: - instead of using it's name for tracing unregistered bdi we just use "unknown" - btrfs and ceph can just assign the default read ahead window themselves like several other filesystems already do. - we can assign noop_backing_dev_info as the default one in alloc_super. All filesystems already either assigned their own or noop_backing_dev_info. Signed-off-by: Christoph Hellwig Reviewed-by: Tejun Heo Reviewed-by: Jan Kara Signed-off-by: Jens Axboe --- include/linux/backing-dev.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux/backing-dev.h') diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index ed59dee03a71..d94077fea1f8 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -241,7 +241,6 @@ int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio); #define BDI_CAP_NO_ACCT_AND_WRITEBACK \ (BDI_CAP_NO_WRITEBACK | BDI_CAP_NO_ACCT_DIRTY | BDI_CAP_NO_ACCT_WB) -extern struct backing_dev_info default_backing_dev_info; extern struct backing_dev_info noop_backing_dev_info; int writeback_in_progress(struct backing_dev_info *bdi); -- cgit v1.2.3 From 0ae45f63d4ef8d8eeec49c7d8b44a1775fff13e8 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Mon, 2 Feb 2015 00:37:00 -0500 Subject: vfs: add support for a lazytime mount option Add a new mount option which enables a new "lazytime" mode. This mode causes atime, mtime, and ctime updates to only be made to the in-memory version of the inode. The on-disk times will only get updated when (a) if the inode needs to be updated for some non-time related change, (b) if userspace calls fsync(), syncfs() or sync(), or (c) just before an undeleted inode is evicted from memory. This is OK according to POSIX because there are no guarantees after a crash unless userspace explicitly requests via a fsync(2) call. For workloads which feature a large number of random write to a preallocated file, the lazytime mount option significantly reduces writes to the inode table. The repeated 4k writes to a single block will result in undesirable stress on flash devices and SMR disk drives. Even on conventional HDD's, the repeated writes to the inode table block will trigger Adjacent Track Interference (ATI) remediation latencies, which very negatively impact long tail latencies --- which is a very big deal for web serving tiers (for example). Google-Bug-Id: 18297052 Signed-off-by: Theodore Ts'o Signed-off-by: Al Viro --- include/linux/backing-dev.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux/backing-dev.h') diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 5da6012b7a14..4cdf7336f64a 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -55,6 +55,7 @@ struct bdi_writeback { struct list_head b_dirty; /* dirty inodes */ struct list_head b_io; /* parked for writeback */ struct list_head b_more_io; /* parked for more writeback */ + struct list_head b_dirty_time; /* time stamps are dirty */ spinlock_t list_lock; /* protects the b_* lists */ }; -- cgit v1.2.3